scholarly journals A Low-Rank Tensor Model for Hyperspectral Image Sparse Noise Removal

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 62120-62127 ◽  
Author(s):  
Lizhen Deng ◽  
Hu Zhu ◽  
Yujie Li ◽  
Zhen Yang
Keyword(s):  
Hyperspectral Image ◽  
Noise Removal ◽  
Low Rank ◽  
Tensor Model ◽  
Rank Tensor

Hyperspectral image compressive reconstruction with low-rank tensor constraint

2020 ◽  
Vol 29 (02) ◽  
pp. 1 ◽  
Author(s):  
Yangyang Li ◽  
Jianping Zhang ◽  
Guiling Sun ◽  
Shijie Wang
Keyword(s):  
Hyperspectral Image ◽  
Low Rank ◽  
Rank Tensor

Hyperspectral Image Restoration Using Low-Rank Tensor Recovery

2017 ◽  
Vol 10 (10) ◽  
pp. 4589-4604 ◽  
Author(s):  
Haiyan Fan ◽  
Yunjin Chen ◽  
Yulan Guo ◽  
Hongyan Zhang ◽  
Gangyao Kuang
Keyword(s):  
Image Restoration ◽  
Hyperspectral Image ◽  
Low Rank ◽  
Rank Tensor ◽  
Tensor Recovery

scholarly journals Hyperspectral Image Destriping and Denoising Using Stripe and Spectral Low-Rank Matrix Recovery and Global Spatial-Spectral Total Variation

2021 ◽  
Vol 13 (4) ◽  
pp. 827
Author(s):  
Fang Yang ◽  
Xin Chen ◽  
Li Chai
Keyword(s):  
Image Denoising ◽  
Gaussian Noise ◽  
Hyperspectral Image ◽  
Noise Removal ◽  
Low Rank ◽  
Matrix Recovery ◽  
Tv Regularization ◽  
Rank Matrix ◽  
Low Rank Matrix Recovery ◽  
Low Rank Matrix

Hyperspectral image (HSI) is easily corrupted by different kinds of noise, such as stripes, dead pixels, impulse noise, Gaussian noise, etc. Due to less consideration of the structural specificity of stripes, many existing HSI denoising methods cannot effectively remove the heavy stripes in mixed noise. In this paper, we classify the noise on HSI into three types: sparse noise, stripe noise, and Gaussian noise. The clean image and different types of noise are treated as independent components. In this way, the image denoising task can be naturally regarded as an image decomposition problem. Thanks to the structural characteristic of stripes and the low-rank property of HSI, we propose to destripe and denoise the HSI by using stripe and spectral low-rank matrix recovery and combine it with the global spatial-spectral TV regularization (SSLR-SSTV). By considering different properties of different HSI ingredients, the proposed method separates the original image from the noise components perfectly. Both simulation and real image denoising experiments demonstrate that the proposed method can achieve a satisfactory denoising result compared with the state-of-the-art methods. Especially, it outperforms the other methods in the task of stripe noise removal visually and quantitatively.

Sign in / Sign up

Export Citation Format

Share Document